Closed AmahleandElihle closed 1 year ago
the ticket makes me very happy
Once you have reached Model_creation_models_for_a_stock.py,
it is because you have executed steps 1 and 2 before.
What error do you get? You can write me at leciluis@gmial.com , so I can help you via telegram.
plots_relations/best_selection_GOOG_neg.json
, this is because you have not executed step 2
in Model_creation_scoring.py
list_stocks = a_manage_stocks_dict.DICT_COMPANYS[CSV_NAME]
list_stocks have to contain "GOOG" ticket
more details https://github.com/Leci37/stocks-prediction-Machine-learning-RealTime-telegram#2-filtering-technical-
I am developing another branch with multidimensional preconditions (4h time thresholds) instead of the published single-dimension one (15min time thresholds). I mean, the multidimensional one makes the operational prediction from all the technical patterns, in a 4h segment (e.g. from 9:00 to 11:00), the mono dimensional one (this document) only takes all the technical patterns given at 11:00. If you are interested in collaborating in it, please send me an email ,
for more info search "stocks-prediction-multi" in this Readme
Feature_selection_json_columns.py has been deleted in newest version, Model_creation_models_for_a_stock.py cannot run success
new pipeline need to fix some code, now it run success, thanks for your excellent job, i will learn more details these day.
Good morning ,
I have just updated the documentation and the erroneous paths , you can see it at https://github.com/Leci37/stocks-prediction-Machine-learning-RealTime-telegram/tree/master#quick-start-up-run-your-own-models I'm closing the ticket.
P.S.: I always welcome a second opinion on https://github.com/Leci37/stocks-prediction-Machine-learning-RealTime-telegram/tree/master#possible-improvements
@Leci37 good work, I'm trying to deploy model by running the file Model_creation_models_for_a_stock.py, it's looking for json which are not populated.
Please assist on how one can generate them.
We also be contributing this work once we get the pipeline working. It was a bit hard to get to Model_creation_models_for_a_stock.py but we did. Many thanks, A&E